Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Update Google Images cover download plugin for website changes. Fixes #2069553 [Version 7.12 no longer downloading cover images from all sources](https://bugs.launchpad.net/calibre/+bug/2069553)

Browse Source
This commit is contained in:
Kovid Goyal 2024-06-17 09:22:45 +05:30
parent 0d611c65f7
commit 43121af37d
No known key found for this signature in database
GPG Key ID: 06BC317B515ACE7C
1 changed files with 28 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
src/calibre/ebooks/metadata/sources/google_images.py
View File

@ -43,10 +43,26 @@ def imgurl_from_id(raw, tbnid):
return q return q
def parse_google_markup(raw):
root = parse_html(raw)
# newer markup pages use data-docid not data-tbnid
results = root.xpath('//div/@data-tbnid') or root.xpath('//div/@data-docid')
ans = OrderedDict()
for tbnid in results:
try:
imgurl = imgurl_from_id(raw, tbnid)
except Exception:
continue
if imgurl:
ans[imgurl] = True
return list(ans)
class GoogleImages(Source): class GoogleImages(Source):
name = 'Google Images' name = 'Google Images'
version = (1, 0, 5) version = (1, 0, 6)
minimum_calibre_version = (2, 80, 0) minimum_calibre_version = (2, 80, 0)
description = _('Downloads covers from a Google Image search. Useful to find larger/alternate covers.') description = _('Downloads covers from a Google Image search. Useful to find larger/alternate covers.')
capabilities = frozenset(['cover']) capabilities = frozenset(['cover'])
@ -88,8 +104,6 @@ class GoogleImages(Source):
from urllib.parse import urlencode from urllib.parse import urlencode
except ImportError: except ImportError:
from urllib import urlencode from urllib import urlencode
from collections import OrderedDict
ans = OrderedDict()
br = self.browser br = self.browser
q = urlencode({'as_q': ('%s %s'%(title, author)).encode('utf-8')}) q = urlencode({'as_q': ('%s %s'%(title, author)).encode('utf-8')})
if isinstance(q, bytes): if isinstance(q, bytes):
@ -116,21 +130,17 @@ class GoogleImages(Source):
raw = clean_ascii_chars(br.open(url).read().decode('utf-8')) raw = clean_ascii_chars(br.open(url).read().decode('utf-8'))
# with open('/t/raw.html', 'w') as f: # with open('/t/raw.html', 'w') as f:
# f.write(raw) # f.write(raw)
root = parse_html(raw) return parse_google_markup(raw)
results = root.xpath('//div/@data-tbnid') # could also use data-id
# from calibre.utils.ipython import ipython
# ipython({'root': root, 'raw': raw, 'url': url, 'results': results})
for tbnid in results:
try:
imgurl = imgurl_from_id(raw, tbnid)
except Exception:
continue
if imgurl:
ans[imgurl] = True
return list(ans)
def test(): def test_raw():
import sys
raw = open(sys.argv[-1]).read()
for x in parse_google_markup(raw):
print(x)
def test(title='Star Trek: Section 31: Control', authors=('David Mack',)):
try: try:
from queue import Queue from queue import Queue
except ImportError: except ImportError:
@ -141,9 +151,9 @@ def test():
p = GoogleImages(None) p = GoogleImages(None)
p.log = default_log p.log = default_log
rq = Queue() rq = Queue()
p.download_cover(default_log, rq, Event(), title='The Heroes', p.download_cover(default_log, rq, Event(), title=title, authors=authors)
authors=('Joe Abercrombie',))
print('Downloaded', rq.qsize(), 'covers') print('Downloaded', rq.qsize(), 'covers')
if __name__ == '__main__': if __name__ == '__main__':
test() test()